We study a feed-forward neural network for two independent function approximation tasks. Upon training, two modules are automatically formed in the hidden layers, each handling one of the tasks predominantly. We demonstrate that the sizes of the modules can be dynamically driven by varying the complexities of the tasks. The network serves as a simple example of an artiicial neural network with ...

Recently, the speech recognition is very attractive for researchers because of the very significant related applications. For this reason, the novel research has been of very importance in the academic community. The aim of this work is to find out a new and appropriate feature extraction method for Arabic language recognition. In the present study, wavelet packet transform (WPT) with modular a...

Few-shot learning (FSL) aims to classify images under low-data regimes, where the conventional pooled global feature is likely lose useful local characteristics. Recent work has achieved promising performances by using deep descriptors. They generally take all descriptors from neural networks into consideration while ignoring that some of them are useless in classification due their limited rec...

The N30 component of the somatosensory evoked potential is known to be modulated by sensory interference, motor action, movement ideation and observation. We introduce a new paradigm in which the observation task of another person's hand movement triggers the somatosensory stimulus, inducing the N30 response in participants. In order to identify the possible contribution of the mirror neuron ne...

Location management is one of the key issues in mobile networks to provide an efficient and low-cost services. In this paper, we propose a prediction-based location management scheme for locating a mobile host (MH), which depends on its history of movement pattern. A multilayer neural network (MNN) model for mobile movement prediction is designed to predict the future movement of a mobile host....

This paper presents a model for the probability of correct classification for the Cooperative Modular Neural Network (CMNN). The model enables the estimation of the performance of the CMNN using parameters obtained from the data set. The performance estimates for the experiments presented are quite accurate (less than 1% relative difference). We compare the CMNN with a multilayer perceptron wit...

Extrapolating the von Neuman’s random-pulse machine concept, the paper discusses the multibit random-data representation and shows how it can be used for the modular design of robust instrumentation for real-time statistical parameter estimation and especially of hardware neural networks.